[codex] Make GTM Agent brief-native#2
Open
a3fckx wants to merge 2 commits into
Open
Conversation
|
Ready to review this PR? Stage has broken it down into 8 individual chapters for you: Chapters generated by Stage for commit 681fc02 on May 13, 2026 5:01am UTC. |
Final state of julep-ai/mem-plugins before plugin set migrates to MemoryStore/plugins. Includes brief-native GTM Agent rewrite, refreshed Memory Store basics/LinkedIn Studio/Marketplace Operator skills, new operating + install reproduction docs, and updated marketplace metadata. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What changed
campaigns/memory-store-first-gtmcampaign workspace from the plugin repo.brief-operating-surface.mdto make the GTM Agent contract explicit: briefs are current operating truth, recall retrieves evidence, records carry confirmed learning/events, and local files are temporary execution ledgers.Why
The previous PR made the Memory Store brief contract stronger, but the committed first-campaign folder made the repo look like one static campaign artifact instead of a reusable GTM engineering system. Briefs should now be the product surface; campaign files should be optional runtime/workspace material.
Validation
python3 -m json.tool plugins/gtm-agent/evals/memory-contract-checks.json >/dev/nullpython3 -m json.tool plugins/gtm-agent/evals/skill-routing-cases.json >/dev/nullpython3 plugins/gtm-agent/scripts/validate_skill_surface.pypython3 plugins/gtm-agent/skills/campaign-setup/scripts/test_render_gtm_plan_template.pygit diff --checkgit diff --cached --checknode /Users/a3fckx/.codex/plugins/cache/openai-curated/plugin-eval/63976030/scripts/plugin-eval.js analyze plugins/gtm-agent --format markdownNotes
Plugin Eval still reports GTM Agent as 72/C because the overall deferred reference surface is heavy (
deferred_cost_tokensaround 44.5k). This PR reduces repo artifact bloat by 1,518 net lines, but it does not attempt the larger reference-budget refactor.